Skip to content
Vijay Work Resume Blog Contact

Resume

Agentic Systems and Workflow View

This view highlights agent orchestration, subgraph design, structured node-to-node state, metadata context, governed query execution, answer reasoning, and visualization workflows where the agent helps users work with data without becoming the data boundary.

Switch views to highlight different aspects of the same experience: AI agents, data platforms, backend engineering, or access governance. Current content refreshed September 2026.

Download Agentic PDF Download Agentic DOCX See related projects

Role views

Choose the role view.

Current view: Agentic . The page and PDF stay aligned around the selected evidence.

Backend platform Service ownership, data APIs, and production reliability. Data platform Pipelines, mesh foundations, streaming, and governance. AI data products Governed agents, text-to-data, visualization, and Python.

Fine tune by focus

General AI Agentic Backend Platform Data Platform
Overall profile

Projects

Relevant projects

Governed conversational data platform

I architected and built a governed conversational data and visualization agent: it retrieves business knowledge, answers business questions, runs governed queries from that context, reasons over results, and builds charts without making the LLM the data boundary.

LangGraph MCP (Model Context Protocol) Python FastAPI

Moved analytics discovery toward self-service by connecting a multi-LLM graph runtime with knowledge retrieval, governed Trino execution, answer reasoning, chart generation, prompt tracing, and a richer Open WebUI experience. The natural-language analytics path reduced query time by about 40% for supported workflows.

Read case study

Access governance platform

Sole architect and lead developer of an enterprise access governance platform: centralized attribute management, policy authoring for OPA/Ranger/OpenFGA, cryptographically signed bundle distribution, and enforcement that keeps working with the control plane offline.

OPA (Open Policy Agent) Apache Ranger Postgres Kubernetes (OCP)

Unified access control across a large telecom enterprise's data infrastructure: attributes from multiple systems of record under one roof, policies authored once and compiled for each enforcement engine, signed bundles shipped to local PDPs for sub-millisecond decisions. Full audit trail and approval workflows for every change.

Read case study

Telecom network data lake

Designed and implemented data lake and warehouse foundations for mobile tower network events at petabyte scale and roughly five trillion events per day.

Flink Kafka Java Elastic Stack

Created the analytics foundation for network data products, reporting, and large-scale downstream consumption.

Read case study

Hive metastore synchronization and metadata governance

Designed and built services that keep Hive metadata consistent across independent environments using real-time listener sync, daily reconciliation, expiry cleanup, one-time interval jobs, observability, and deployment hardening.

Java Spark Airflow Apache Hive

Turned fragile metadata drift into an owned synchronization path with real-time event propagation, reconciliation, recovery behavior, logs, and platform deployment controls.

Read case study

Experience

Relevant experience

Data Platform Engineer / Architect · Airtel Digital

I architect and build governed data platforms, metadata services, workflow orchestration, access-governance integrations, in-house CI/CD onboarding, and network-scale analytics systems.

2021 - present

  • Architected and built a governed conversational data platform for text-to-data workflows: multi-LLM subgraphs, knowledge retrieval, controlled query execution, answer reasoning, chart generation, prompt tracing, and platform orchestration.
  • Designed and implemented Hive metadata synchronization for independent Hive environments, combining real-time listener sync, daily reconciliation, missed-addition/removal repair, sync-duration expiry cleanup, one-time interval jobs, observability, and deployment hardening.
  • Built governed self-service data platform capabilities around Kyuubi customizations, Trino query access, DataHub metadata, dbt transformations, Metabase BI, RBAC, and secrets management.

Data Science Engineer · dunnhumby

I worked between data science and big-data platform teams, turning statistical and ML analysis into reusable pipelines, data marts, reporting products, and client-ready analytics workflows.

2018 - 2021

  • Worked as a bridge between data science and big data platform teams by turning analytical work into reusable products and repeatable pipelines.
  • Built customer segmentation, data marts, reporting platforms, and retail optimization analytics for large datasets, including category/adjacency work associated with up to 20% sales-growth impact.
  • Created reusable retail analytics workflows across customer priority assortment, cross-shopping behavior, direct-mail promotion planning, category uplift, and seasonality analysis.

Software Engineer · Mphasis

I worked on mainframe and big-data systems for insurance and telecom clients, including Spark migration work and automation that saved 500+ manual hours per year.

2014 - 2018

  • Worked in both mainframe and big data ecosystems and contributed to migration from mainframe workloads to Spark-based processing.
  • Built automations that saved 500+ manual hours per year by removing repetitive workflow steps.
  • Worked as a developer for insurance and telecom clients across enterprise systems and data workflows.

Skill stack

Primary skills

Multi-Agent Systems Agent Harness Tool Use & Function Calling LLM Orchestration Agent Orchestration LangGraph MCP (Model Context Protocol) Python

Supporting skills

AI Evals Context Engineering RAG Vector Search Prompt Engineering Langfuse

Additional skills

FastAPI Generative AI Open WebUI Postgres Next.js JavaScript